Mechanistic Data Attribution: Tracing the Training Origins of Interpretable LLM Units
Paper
•
2601.21996
•
Published
•
3
Jianhui Chen
JianhuiChen
AI & ML interests
None yet
Recent Activity
submitted
a paper
2 days ago
Mechanistic Data Attribution: Tracing the Training Origins of Interpretable LLM Units
authored
a paper
2 days ago
MAVEN-Arg: Completing the Puzzle of All-in-One Event Understanding
Dataset with Event Argument Annotation
Organizations
None yet
submitted
a
paper
to Daily Papers
2 days ago
authored
3
papers
2 days ago
MAVEN-Arg: Completing the Puzzle of All-in-One Event Understanding Dataset with Event Argument Annotation
Paper
•
2311.09105
•
Published
KoLA: Carefully Benchmarking World Knowledge of Large Language Models
Paper
•
2306.09296
•
Published
•
19
Are Reasoning Models More Prone to Hallucination?
Paper
•
2505.23646
•
Published
•
24